Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1787 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3990. Min Range: -9.3990
Max Act: 9.3990. Min Act: -0.1700
Data Index: 6860713 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.8990. Min Act: -0.1700
Data Index: 6722725 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.8990. Min Act: -0.1700
Data Index: 8298249 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.8365. Min Act: -0.1700
Data Index: 3295752 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.7115. Min Act: -0.1700
Data Index: 5653964 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.7740. Min Act: -0.1700
Data Index: 7590926 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.7740. Min Act: -0.1700
Data Index: 5150250 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.7115. Min Act: -0.1700
Data Index: 935277 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.7115. Min Act: -0.1700
Data Index: 2017250 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.7115. Min Act: -0.1700
Data Index: 3518056 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.6490. Min Act: -0.1700
Data Index: 8447799 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.6490. Min Act: -0.1700
Data Index: 296363 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.6490. Min Act: -0.1700
Data Index: 3246353 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.6490. Min Act: -0.1700
Data Index: 4777718 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.5865. Min Act: -0.1700
Data Index: 3766861 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.6490. Min Act: -0.1700
Data Index: 997686 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.5865. Min Act: -0.1700
Data Index: 3167843 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.5865. Min Act: -0.1700
Data Index: 3911572 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.5865. Min Act: -0.1700
Data Index: 2380724 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3990. Min Range: -9.3990
Max Act: 8.5865. Min Act: -0.1700
Data Index: 6490462 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19